Method, device, equipment and system for determining cable force of bridge stay cable and medium

Abstract

The invention relates to the technical field of bridge maintenance, in particular to a bridge stay cable force determination method, device, equipment, system and medium, data acquisition is carried out multiple times before a shock absorber is installed so as to form a first data set, and for the same stay cable, after the shock absorber is installed, a second data set is formed; at the position away from the connection position of the stay cable and the shock absorber by a preset distance, data collection is conducted on the stay cable multiple times to form a second data set, the first data set and the second data set are jointly input into the target neural network model for prediction, and a cable force result of the stay cable is obtained. A first data set collected before installation of a shock absorber and a second data set collected after installation of the shock absorber are used as input data, and the input data are input to a target neural network for prediction operation, so that accurate calculation of the cable force of the stay cable can be realized; and the precision of obtaining the cable force of the stay cable provided by the shock absorber is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge maintenance, and in particular to a method, device, equipment, system and medium for determining the cable force of a bridge stay cable. Background Art

[0002] As an important load-bearing component in a long-span bridge structure, the cable tension state is directly related to the overall safety and stability of the bridge. Therefore, accurately and efficiently identifying the cable tension of the cable has become one of the key technologies in the field of bridge health monitoring and maintenance. The development of cable tension identification technology has undergone an evolution from empirical formula estimation, vibration frequency method to the combination of modern sensor technology and signal processing algorithm.

[0003] In the early days, engineers mainly relied on empirical formulas and simple mechanical models to estimate the cable force of the inclined cable. Although this method is simple and easy to use, it has low accuracy and is difficult to adapt to complex and changeable bridge structures. Subsequently, the vibration frequency method has gradually been widely used due to its solid theoretical basis and simple measurement. This method measures the vibration frequency of the inclined cable and combines the inherent vibration characteristics of the cable (such as mode, damping, etc.) to deduce the cable force value. However, the vibration frequency method is still restricted by many factors in practical applications, such as environmental noise, temperature influence, changes in boundary conditions, etc., all of which may affect the accuracy of the measurement results.

[0004] The accuracy of cable force measurement and identification is of great significance for the safety monitoring of cable-stayed bridges during construction and operation. The frequency method has been widely used in practical engineering due to its convenience and speed. However, its accuracy is affected by the shock absorber. For the cable-stayed cables with shock absorbers installed, the error of identifying the cable force using the existing frequency method is large due to the coupling influence of various factors. At the same time, the existence of the shock absorber has a certain impact on the vibration of the cable. The equivalent length method, energy method, etc. have poor generalization ability and unsatisfactory accuracy in identifying the cable force of the cable with shock absorbers in different engineering applications. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, equipment, system and medium for determining the cable tension of a bridge cable, aiming to solve the technical problems in the related technology that the existence of the shock absorber causes a certain influence on the vibration of the cable, and the equivalent length method, energy method, etc. have poor generalization ability and unsatisfactory accuracy in identifying the cable tension of the cable with shock absorber in different engineering applications.

[0006] To achieve the above purpose, the present application proposes a method for determining the cable force of a bridge, comprising the following steps:

[0007] Before the shock absorber is installed, multiple data collections are performed to form a first data set; wherein the first data set includes an initial cable frequency, an initial cable force, and an initial order;

[0008] For the same stay cable, after the shock absorber is installed, data of the stay cable is collected multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber to form a second data group; wherein the second data group includes a current frequency of the stay cable after the shock absorber is installed, a steel strand density of the stay cable, and a length of the stay cable;

[0009] The first data group and the second data group are input into a target neural network model for prediction to obtain the cable force result of the inclined cable.

[0010] In one embodiment, before the step of inputting the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable, the step further includes:

[0011] The wolf pack algorithm is used to optimize the long short-term memory neural network to obtain the objective function; wherein the objective function is expressed by formula 1, which is:

[0012] F i =f(d,L,E,θ,…;p)

[0013] F i is the cable force of the inclined cable, d is the deflection of the main beam of the bridge, L is the length of the inclined cable of the bridge, E is the elastic modulus of the material of which the inclined cable is made, θ is the environmental parameter affecting the cable force, and p is the model parameter vector;

[0014] A loss function is introduced to perform secondary processing on the objective function to obtain the target neural network; wherein the loss function is expressed by Formula 2, which is:

[0015]

[0016] J(P) is the cable force accuracy result of each target measurement point, is the predicted cable force when the parameter P is used at the corresponding target measurement point, is the measured cable force at the corresponding target measurement point, and N is the number of the target measurement points.

[0017] In one embodiment, the step of introducing a loss function to perform secondary processing on the target function to obtain the target neural network includes:

[0018] A mathematical model of a wolf pack optimization algorithm is established; wherein the mathematical model of the wolf pack optimization algorithm is expressed by Formula 3, which is:

[0019] X i (t+1)=X α (t)-A α C α D α

[0020] X i (t+1)=X β (t)-A β C β D β

[0021] X i (t+1)=X δ (t)-A δ C δ D δ

[0022] X i (t+1) is the position vector of the i-th search agent at the t+1th iteration, X α (t) is the position vector of the first leader wolf at the t+1th iteration, X β (t) is the position vector of the second leader wolf at the t+1th iteration, X δ (t) is the position vector of the third leader wolf at the t+1th iteration, A and C are coefficient vectors, D is the distance vector, A is expressed using Formula 4, C is expressed using Formula 5, and D is expressed using Formula 6. Formula 4 is:

[0023] A=2ar1-a

[0024] The formula five is:

[0025] C=2r2

[0026] The formula six is:

[0027] D=|C a X α (t)-x i (t)|

[0028] a is a parameter that decreases linearly from 2 to 0, r1 and r2 are random vectors in the interval [0,1];

[0029] The target neural network is obtained by using the wolf pack optimization algorithm mathematical model and introducing the loss function to perform secondary processing on the target function.

[0030] In one embodiment, the step of using the wolf pack optimization algorithm mathematical model and introducing the loss function to perform secondary processing on the objective function to obtain the target neural network includes:

[0031] Initialize the wolf pack optimization algorithm to select q initial alpha wolves from N randomly generated artificial wolves; wherein N is a positive integer greater than or equal to 2, q is a positive integer greater than or equal to 1 and less than N,

[0032] Determine a target alpha wolf from the q initial alpha wolves;

[0033] The target neural network is obtained by adaptively iterating and optimizing the target number of operations of the target function through the calling behavior of the target leader wolf and the introduction of the loss function to complete the secondary processing.

[0034] In one embodiment, the step of initializing the wolf pack optimization algorithm to select q initial alpha wolves from N randomly generated artificial wolves includes:

[0035] Initializing the wolf pack optimization algorithm to determine the second target parameters of the wolf pack optimization algorithm; wherein the parameters include the size of the wolf pack, the dimension of the search space, the number of iterations, the step size factor, the wolf exploration scale factor, and the group update scale factor;

[0036] According to the second target parameter, randomly generating N artificial wolves in the solution space;

[0037] The objective function value of each artificial wolf is obtained in turn, and q artificial wolves that only meet preset conditions are screened out from the N objective function values ​​to serve as the initial leader wolf.

[0038] In one embodiment, for the same stay cable, after the shock absorber is installed, the step of collecting data of the stay cable multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber to form a second data set includes:

[0039] For the same inclined cable, a shock absorber is installed on the inclined cable;

[0040] After installing the shock absorber, using a rubber hammer to perform multiple manual hammer excitations at any position on the cable;

[0041] And after a preset time interval, data of the stay cable is collected multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber to form a second data group.

[0042] Based on the same technical concept, in a second aspect, the present invention further proposes a device for determining the cable force of a bridge stay cable, comprising:

[0043] A first data acquisition module, used for performing multiple data acquisitions before the shock absorber is installed to form a first data group; wherein the first data group includes an initial cable frequency, an initial cable force and an initial order;

[0044] A second data collection module is used for collecting data of the same stay cable for multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber after the shock absorber is installed, so as to form a second data group;

[0045] The result output module is used to input the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable.

[0046] Based on the same technical concept, in the third aspect, the present invention also proposes a device for determining the force of a bridge cable, the device comprising a processor and a memory, the memory storing a program for determining the force of a bridge cable, and when the program for determining the force of a bridge cable is executed by the processor, the method for determining the force of a bridge cable described in the first aspect is implemented.

[0047] Based on the same technical concept, in a fourth aspect, the present invention further proposes a bridge cable force determination system, wherein a shock absorber is provided on the cable, and a connection position between the shock absorber and the cable forms a detection position;

[0048] The bridge stayed cable force determination system comprises:

[0049] The device for determining the force of the bridge cable according to the first aspect;

[0050] A collection sensor, wherein the collection sensor is installed on the inclined cable, and the collection sensor is spaced apart from the detection position; and

[0051] A data acquisition device is communicatively connected with the acquisition sensor and transmits the acquired data information to the bridge cable force determination device.

[0052] Based on the same technical concept, in the fifth aspect, the present invention further proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by one or more processors, the method for determining the cable tension of a bridge cable described in the first aspect is implemented.

[0053] One or more technical solutions proposed in this application have at least the following technical effects:

[0054] The technical solution of the present application is to collect data multiple times before the shock absorber is installed to form a first data group. For the same inclined cable, after the shock absorber is installed, data is collected multiple times on the inclined cable at a position preset distance from the connection position between the inclined cable and the shock absorber to form a second data group. The first data group and the second data group are input into a target neural network model for prediction to obtain the cable force result of the inclined cable. When the present invention is used, the first data group collected before the shock absorber is installed and the second data group collected after the shock absorber is installed are used as input data, and the input data are input into the target neural network for prediction. Therefore, the present invention can realize accurate prediction of the cable force of the inclined cable, and improve the recognition accuracy of the cable force of the shock absorber. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 A flow chart of a method for determining the cable force of a bridge cable according to an example of this application;

[0058] Figure 2 Flow charts of some specific embodiments of the present invention;

[0059] Figure 3 for Figure 2 A flow chart of step S500 in the example;

[0060] Figure 4 for Figure 3 Schematic diagram of the process of step S520 in the example;

[0061] Figure 5 for Figure 4 Schematic diagram of the process of step S521 in the example;

[0062] Figure 6 This is a schematic diagram of the structure of the device for determining the cable force of the bridge cable used as an example in this application.

[0063] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0064] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0065] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0066] See also Figures 1 to 6 The present application proposes a first embodiment of a method for determining the cable force of a bridge, comprising the following steps:

[0067] S100, before the shock absorber is installed, perform multiple data collection to form a first data group; wherein the first data group includes an initial cable frequency, an initial cable force, and an initial order;

[0068] S200, for the same inclined cable, after the shock absorber is installed, collect data of the inclined cable multiple times at a position at a preset distance from a connection position between the inclined cable and the shock absorber to form a second data group; wherein the second data group includes a current frequency of the inclined cable after the shock absorber is installed, a steel strand density of the inclined cable, and a length of the inclined cable;

[0069] S300, inputting the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable.

[0070] In this embodiment, multiple data collections are performed before the shock absorber is installed to form a first data group. For the same cable, after the shock absorber is installed, multiple data collections are performed on the cable at a preset distance from the connection position between the cable and the shock absorber to form a second data group. The first data group and the second data group are input into the target neural network model for prediction to obtain the cable force result of the cable. When the present invention is in use, the first data group collected before the shock absorber is installed and the second data group collected after the shock absorber is installed are used as input data, and the input data is input into the target neural network for prediction. Therefore, the present invention can realize accurate prediction of the cable force, thereby improving the recognition accuracy of the cable force of the shock absorber.

[0071] In one embodiment, before step S300, the method further includes:

[0072] S400, using a wolf pack algorithm to perform optimization processing on the long short-term memory neural network to obtain an objective function; wherein the objective function is expressed by formula 1, and formula 1 is:

[0073] F i =f(d,L,E,θ,…;p)

[0074] F i is the cable force of the inclined cable, d is the deflection of the main beam of the bridge, L is the length of the inclined cable of the bridge, E is the elastic modulus of the material making the inclined cable, θ is the environmental parameter affecting the cable force, and p is the model parameter vector.

[0075] In this embodiment, during specific implementation, the construction process of Formula 1 is:

[0076] Due to formula F i =f(d,L,E,θ,…;p) is a general function expression used to describe the cable force F i The mathematical relationship between the factors that influence it. In this formula, f is a specific (but possibly unknown or complex) function that depends on multiple variables and parameters. Here is a detailed explanation of each parameter:

[0077] d is the main beam deflection, which represents the vertical displacement of the main beam when it is subjected to external force.

[0078] In the process of determining the cable force, the main beam deflection will directly affect the tension of the cable because the cable is usually connected to the main beam and bears the load together.

[0079] L is the length of the cable, which is expressed as the straight-line distance from one anchor point to the other anchor point of the cable.

[0080] In the process of determining the cable force, the length of the cable will affect the stiffness and force distribution of the cable, and thus affect the size of the cable force.

[0081] E is the elastic modulus of the material, which is expressed as the ratio of stress to strain of the cable material within the elastic range.

[0082] In the process of determining the cable tension, the elastic modulus determines the ability of the cable to resist deformation when subjected to tension and is an important parameter for calculating the cable tension.

[0083] θ is the angle between the cable and the horizontal plane, which is expressed as the angle between the cable and the horizontal plane of the bridge.

[0084] In the process of determining the cable force, the change of the angle will change the horizontal and vertical components of the cable, thereby affecting the magnitude of the cable force.

[0085] Of course, in order to make the cable force results more accurate, other parameters such as the cross-sectional area of ​​the cable, the temperature effect coefficient, the geometric characteristics of the bridge structure, etc. can be introduced in the specific calculation process. As for how to select parameters in different environments, it depends on the complexity and accuracy requirements of the model.

[0086] P is the model parameter vector, that is, an unknown parameter or a set of parameters, which is used to capture the factors or effects that may exist in the model that are not explicitly quantified, such as the nonlinear behavior of the material, the dynamic response of the structure, etc.

[0087] In the process of determining the cable forces, the adaptability and accuracy of the model are improved so that the model can more realistically reflect the actual situation.

[0088] The overall meaning of formula 1 is to describe the complex mathematical relationship between the cable force and its influencing factors. It is widely used in the fields of bridge engineering, structural mechanics and civil engineering to estimate, monitor and maintain the cable forces in cable-stayed bridges to ensure the safety and stability of the bridges.

[0089] The acquisition process of formula 1 is:

[0090] Since the specific form of f may be very complicated and depends on the specific bridge structure and mechanical model, only a simplified derivation example is given here. Please note that this example may not be directly applicable to all situations.

[0091] Assume that the cable is an ideal elastic body and obeys Hooke's law.

[0092] Ignore the deadweight of the cables and other non-essential loads.

[0093] It is assumed that there is some simple geometric relationship between the deflection d of the main beam and the elongation ΔL of the inclined cable (this is usually an approximation).

[0094] Hooke's law is used to express the mathematical relationship between stress and cable force, specifically:

[0095]

[0096] Where σ is stress, F is cable force, A is the cross-sectional area of ​​the cable, E is the elastic modulus, and ∈ is strain (i.e., the ratio of elongation to original length).

[0097] The mathematical relationship between strain and elongation is determined as follows:

[0098]

[0099] Combining Hooke's law and the strain relationship:

[0100]

[0101] Consider the geometric relationship:

[0102] Assume that the geometric relationship between the main beam deflection d and the cable elongation ΔL is (this is usually an approximation or requires experimental verification):

[0103] ΔL=d·sinθ·(a coefficient related to the bridge structure)

[0104] For simplicity, temporarily ignore this coefficient and get:

[0105] ΔL=d·sinθ

[0106] Substituting into the cable force formula, we can get:

[0107]

[0108] By introducing the model parameter vector P, the objective function can be obtained.

[0109] Of course, in specific implementation, if other factors need to be considered (such as temperature effect, relaxation of the inclined cable, etc.), additional terms or parameters can be introduced into the above expression.

[0110] Meanwhile, if some parameters (such as A or coefficients related to the bridge structure) are difficult to measure or calculate accurately, they can be regarded as part of the unknown parameters p.

[0111] S500, introducing a loss function to perform secondary processing on the target function to obtain the target neural network; wherein the loss function is expressed by Formula 2, which is:

[0112]

[0113] J(P) is the cable force accuracy result of each target measurement point, is the predicted cable force when the parameter P is used at the corresponding target measurement point, is the measured cable force at the corresponding target measurement point, and N is the number of the target measurement points.

[0114] In one embodiment, step S500 includes:

[0115] S510, establishing a mathematical model of a wolf pack optimization algorithm; wherein the mathematical model of the wolf pack optimization algorithm is expressed by Formula 3, which is:

[0116] X i (t+1)=X α (t)-A α C α D α

[0117] X i (t+1)=X β (t)-A β C β D β

[0118] X i(t+1)=X δ (t)-A δ C δ D δ

[0119] X i (t+1) is the position vector of the i-th search agent at the t+1th iteration, X α (t) is the position vector of the first leader wolf at the t+1th iteration, X β (t) is the position vector of the second leader wolf at the t+1th iteration, X δ (t) is the position vector of the third leader wolf at the t+1th iteration, A and C are coefficient vectors, D is the distance vector, A is expressed using Formula 4, C is expressed using Formula 5, and D is expressed using Formula 6. Formula 4 is:

[0120] A=2ar1-a

[0121] The formula five is:

[0122] C=2r2

[0123] The formula six is:

[0124] D=|C a X α (t)-X i (t)|

[0125] a is a parameter that decreases linearly from 2 to 0, r1 and r2 are random vectors in the interval [0,1];

[0126] S520, using the wolf pack optimization algorithm mathematical model and introducing the loss function to perform secondary processing on the objective function to obtain the target neural network.

[0127] In this embodiment, in order to more clearly understand the present invention, in specific implementation, the specific process of step S520 may be:

[0128] The process of optimizing the cable forces of bridge cables using the Wolf Colony Search Algorithm (WCA) or the Grey Wolf Optimizer (GWO) similar to it involves several key steps. The following is an example of a process based on WCA / GWO, applied to the optimization of the cable forces (i.e. the cable tension) of bridge cables:

[0129] The objective function f(T) should reflect the performance indicators of the bridge structure, such as total deformation energy, stress distribution, displacement control, etc. A common goal is to minimize the total deformation energy of the structure, which can be expressed as:

[0130]

[0131] Among them, E u (T u ) is the tension of the i-th cable T i The deformation energy caused by this equation is T = [T1, T2, ..., Tn], which is the tension vector of all the cables.

[0132] Create an initial population of search agents (i.e., individuals in a wolf pack), one for each combination of cable tensions. These initial values ​​can be randomly generated to ensure coverage of the entire search space.

[0133] Each search agent's cable tension configuration is evaluated using the objective function f(T) to calculate its fitness value. A lower objective function value means better fitness.

[0134] Find the three individuals with the best fitness in the current population for updating iterations, which are α, β and δ respectively. α represents the current best solution.

[0135] Update the position of each search agent according to the mathematical model of WCA / GWO. This involves adjusting the position of each search agent using the position information of α, β, and δ as well as the random coefficient vector and distance vector in the update formula.

[0136] Recalculate the fitness of the updated position to determine whether it is better than the previous position.

[0137] Check whether the predetermined number of iterations has been reached or the fitness improvement is no longer significant. If the stopping condition is not reached, return to find the three individuals with the best fitness in the current population and continue iterating by performing the update iteration step.

[0138] When the stopping condition is met, the position of α wolf is output as the final optimization result, that is, the optimal cable tension configuration.

[0139] It should be noted that during each iteration, it is necessary to ensure that the cable tension value remains within a reasonable engineering range to avoid unrealistic solutions.

[0140] In practical applications, additional constraints may need to be considered, such as material strength limitations, safety requirements, etc.

[0141] Although the wolfpack optimization algorithm is capable of handling nonlinear and multimodal optimization problems, it may require a lot of computing resources and time in high-dimensional and complex spaces.

[0142] Through the above steps, the wolf pack optimization algorithm can be used to accurately calculate the tension of the bridge's cable stays, thereby optimizing the overall performance of the bridge.

[0143] In this embodiment, the wolf pack optimization algorithm mathematical model is used and the loss function is introduced to evaluate the target model to obtain the accuracy result of the cable force of the bridge, so that the calculation accuracy of the cable force can be effectively guaranteed when the present invention is used specifically.

[0144] Of course, in specific implementation, the wolf pack optimization algorithm used in the above embodiments has the following advantages:

[0145] The wolf pack optimization algorithm process is relatively simple, and only needs to simulate the social hierarchy and hunting behavior of gray wolves. This makes the wolf pack optimization algorithm easy to understand and implement, and suitable for various programming environments.

[0146] Compared with other optimization algorithms, the wolfpack optimization algorithm has fewer parameters, mainly including the convergence factor (a) and some random vectors. The setting of these parameters is relatively simple, and the impact on the performance of the algorithm is relatively intuitive, which is convenient for users to adjust according to specific problems.

[0147] The wolf pack optimization algorithm can achieve a good balance between global exploration and local development by adjusting the values ​​of the coordination coefficients (A) and (C). This helps the algorithm to explore the search space extensively in the early stages of the search and discover potential optimal solution areas; in the later stages of the search, it can deeply develop these areas to find the optimal solution.

[0148] Since the wolf pack optimization algorithm simulates the social hierarchy and hunting mechanism of gray wolves, the algorithm has a clear guiding direction in the search process, converges quickly, and ensures computational efficiency. This helps the algorithm converge quickly to the optimal solution and reduces unnecessary search time.

[0149] The wolfpack optimization algorithm has shown good performance in a variety of test functions and practical applications, proving its strong robustness. Even in the face of complex optimization problems, the wolfpack optimization algorithm can find a satisfactory solution by adjusting parameters and strategies.

[0150] The wolf pack optimization algorithm has been successfully applied in many fields, such as function optimization, neural network training, image processing, path planning, etc. This shows that the wolf pack optimization algorithm has strong adaptability and can be flexibly adjusted and optimized according to the characteristics of different problems.

[0151] Since the wolf pack optimization algorithm simulates the gray wolf's behaviors of surrounding, tracking and attacking prey during the search process, the algorithm can conduct a wide search in the entire search space and has a strong global search capability. This helps the algorithm to find potential global optimal solutions and avoid falling into local optimal solutions.

[0152] The wolf pack optimization algorithm simulates the social hierarchy of gray wolves, allowing individuals in the algorithm to collaborate and evolve together. This synergistic advantage helps the algorithm maintain diversity during the search process and improves search efficiency and quality.

[0153] Therefore, the wolf pack optimization algorithm has many advantages, such as simple structure, few parameters, fast convergence speed, strong robustness, strong adaptability, strong global search ability and synergy advantage brought by social hierarchy structure. These advantages make the wolf pack optimization algorithm have broad application prospects and important research value in solving complex optimization problems.

[0154] In one embodiment, step S520 includes:

[0155] S521, initializing the wolf pack optimization algorithm to select q initial alpha wolves from N randomly generated artificial wolves; wherein N is a positive integer greater than or equal to 2, q is a positive integer greater than or equal to 1 and less than N,

[0156] S522, determining a target alpha wolf from the q initial alpha wolves;

[0157] S523, through the calling behavior of the target wolf leader and the introduction of the loss function, the target function is adaptively iterated to optimize the target number of operations to complete the secondary processing and obtain the target neural network.

[0158] In one embodiment, step S521 includes:

[0159] S521a, initializing the wolf pack optimization algorithm to determine the second target parameters of the wolf pack optimization algorithm; wherein the parameters include the size of the wolf pack, the dimension of the search space, the number of iterations, the step size factor, the wolf exploration scale factor, and the group update scale factor;

[0160] S521b, randomly generating N artificial wolves in the solution space according to the second target parameter;

[0161] S521c, sequentially obtaining the objective function value of each of the artificial wolves, and selecting q artificial wolves that only meet preset conditions from the N objective function values ​​as the initial leader wolf.

[0162] In one embodiment, step S200 includes:

[0163] S210, for the same inclined cable, installing a shock absorber on the inclined cable;

[0164] S220, after installing the shock absorber, performing multiple manual hammer excitations at any position on the inclined cable using a rubber hammer;

[0165] S230, and after a preset time interval, collect data of the cable for multiple times at a position at a preset distance from a connection position between the cable and the shock absorber to form a second data set.

[0166] Based on the same technical concept, in a second aspect, the present invention further proposes a device for determining the cable force of a bridge stay cable, comprising:

[0167] A first data acquisition module, used for performing multiple data acquisitions before the shock absorber is installed to form a first data group; wherein the first data group includes an initial cable frequency, an initial cable force and an initial order;

[0168] A second data collection module is used for collecting data of the same stay cable for multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber after the shock absorber is installed, so as to form a second data group;

[0169] The result output module is used to input the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable.

[0170] The bridge cable force determination device provided in the embodiment of the present application adopts the bridge cable force determination method in the above embodiment, which can solve the technical problem that the vibration of the cable is affected to a certain extent by the existence of the shock absorber, and the generalization ability of the equivalent length method, energy method, etc. for identifying the cable force of the cable with shock absorber in different engineering applications is poor and the accuracy is not ideal. Compared with the prior art, the beneficial effects of the bridge cable force determination device provided in the embodiment of the present application are the same as the beneficial effects of the bridge cable force determination method provided in the above embodiment, and the other technical features in the bridge cable force determination device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0171] Based on the same technical concept, in the third aspect, the present invention also proposes a device for determining the force of a bridge cable, the device comprising a processor and a memory, the memory storing a program for determining the force of a bridge cable, and when the program for determining the force of a bridge cable is executed by the processor, the method for determining the force of a bridge cable described in the first aspect is implemented.

[0172] Reference below Figure 6, which shows a schematic diagram of the structure of a bridge cable force determination device suitable for implementing the embodiment of the present application. The bridge cable force determination device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted control terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The bridge cable tension determination device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Figure 6 As shown, the bridge cable force determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. Various programs and data required for the operation of the bridge cable force determination device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the bridge cable force determination device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a bridge cable force determination device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0174] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0175] The bridge cable force determination device provided by the present application adopts the bridge cable force determination method in the above-mentioned embodiment, which can solve the technical problem that the vibration of the cable is affected to a certain extent by the existence of the shock absorber, and the generalization ability of the equivalent length method, energy method, etc. for identifying the cable force of the cable with shock absorber in different engineering applications is poor and the accuracy is not ideal. Compared with the prior art, the beneficial effects of the bridge cable force determination device provided by the present application are the same as the beneficial effects of the bridge cable force determination method provided by the above-mentioned embodiment, and the other technical features in the bridge cable force determination device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0176] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0177] In addition, the bridge cable force determination device provided in the embodiment of the present application can solve the technical problem that the existence of the shock absorber causes a certain influence on the vibration of the cable, and the equivalent length method, energy method, etc. have poor generalization ability and unsatisfactory accuracy in identifying the cable force of the cable with shock absorber in different engineering applications. Compared with the prior art, the beneficial effects of the bridge cable force determination device provided in the embodiment of the present application are the same as the beneficial effects of the bridge cable force determination method provided in the above embodiment, and the other technical features of the bridge cable force determination device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0178] Based on the same technical concept, in a fourth aspect, the present invention further proposes a bridge cable force determination system, wherein a shock absorber is provided on the cable, and a connection position between the shock absorber and the cable forms a detection position;

[0179] The bridge stayed cable force determination system comprises:

[0180] The device for determining the force of the bridge cable according to the first aspect;

[0181] A collection sensor, wherein the collection sensor is installed on the inclined cable, and the collection sensor is spaced apart from the detection position; and

[0182] A data acquisition device is communicatively connected with the acquisition sensor and transmits the acquired data information to the bridge cable force determination device.

[0183] In addition, the bridge cable force determination system provided in the embodiment of the present application can solve the technical problem that the existence of the shock absorber causes a certain influence on the vibration of the cable, and the equivalent length method, energy method, etc. have poor generalization ability and unsatisfactory accuracy in identifying the cable force of the cable with shock absorber in different engineering applications. Compared with the prior art, the beneficial effects of the bridge cable force determination system provided in the embodiment of the present application are the same as the beneficial effects of the bridge cable force determination method provided in the above embodiment, and the other technical features of the bridge cable force determination system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0184] Based on the same technical concept, in the fifth aspect, the present invention further proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by one or more processors, the method for determining the cable tension of a bridge cable described in the first aspect is implemented.

[0185] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0186] The computer-readable storage medium may be included in the device for determining the cable force of a bridge cable; or may exist independently without being assembled into the device for determining the cable force of a bridge cable.

[0187] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the bridge cable force determination device, the bridge cable force determination device can implement the bridge cable force determination method described above.

[0188] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0189] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0190] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0191] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for determining the cable force of a bridge cable, and can solve the technical problem that the existence of the shock absorber causes a certain influence on the vibration of the cable, and the equivalent length method, energy method, etc. have poor generalization ability and unsatisfactory accuracy in identifying the cable force of the cable with shock absorber in different engineering applications. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for determining the cable force of a bridge cable provided by the above-mentioned embodiment, and will not be repeated here.

[0192] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining the cable force of a bridge, characterized in that: The steps include: Before the shock absorber is installed, multiple data collections are performed to form a first data set; wherein the first data set includes an initial cable frequency, an initial cable force, and an initial order; For the same stay cable, after the shock absorber is installed, data of the stay cable is collected multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber to form a second data group; wherein the second data group includes a current frequency of the stay cable after the shock absorber is installed, a steel strand density of the stay cable, and a length of the stay cable; The first data group and the second data group are input into a target neural network model for prediction to obtain the cable force result of the inclined cable.

2. The method for determining the cable force of a bridge according to claim 1, characterized in that: Before the step of inputting the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable, the method further includes: The wolf pack algorithm is used to optimize the long short-term memory neural network to obtain the objective function; wherein the objective function is expressed by formula 1, which is: F i =f(d,L,E,θ,…;p) F i is the cable force of the inclined cable, d is the deflection of the main beam of the bridge, L is the length of the inclined cable of the bridge, E is the elastic modulus of the material of which the inclined cable is made, θ is the environmental parameter affecting the cable force, and p is the model parameter vector; A loss function is introduced to perform secondary processing on the objective function to obtain the target neural network; wherein the loss function is expressed by Formula 2, which is: J(P) is the cable force accuracy result of each target measurement point, is the predicted cable force when the parameter P is used at the corresponding target measurement point, is the measured cable force at the corresponding target measurement point, and N is the number of the target measurement points.

3. The method for determining the cable force of a bridge according to claim 2, characterized in that: The step of introducing a loss function to perform secondary processing on the target function to obtain the target neural network includes: A mathematical model of a wolf pack optimization algorithm is established; wherein the mathematical model of the wolf pack optimization algorithm is expressed by formula three, and the formula three is: X i (t+1)=X α (t)-A α C α D α X i (t+1)=X β (t)-A β c β d β x i (t+1)=X δ (t)-a δ c δ d δ x i (T+1) is the position vector of the I-th search agent at the t+1th iteration, X α (t) is the position vector of the first leader wolf at the t+1th iteration, X β (t) is the position vector of the second leader wolf at the t+1th iteration, X δ (t) is the position vector of the third leader wolf at the t+1th iteration, A and C are coefficient vectors, D is the distance vector, A is expressed using Formula 4, C is expressed using Formula 5, and D is expressed using Formula 6. Formula 4 is: A=2ar1-a The formula five is: C＝2r2 The formula six is: D=|C α X α (t)-X i (t)| a is a parameter that decreases linearly from 2 to 0, r1 and r2 are random vectors in the interval [0,1]; The target neural network is obtained by using the wolf pack optimization algorithm mathematical model and introducing the loss function to perform secondary processing on the target function.

4. The method for determining the cable force of a bridge according to claim 3, characterized in that: The step of using the wolf pack optimization algorithm mathematical model and introducing the loss function to perform secondary processing on the objective function to obtain the target neural network includes: Initialize the wolf pack optimization algorithm to select q initial alpha wolves from N randomly generated artificial wolves; wherein N is a positive integer greater than or equal to 2, q is a positive integer greater than or equal to 1 and less than N, Determine a target alpha wolf from the q initial alpha wolves; The target neural network is obtained by adaptively iterating and optimizing the target number of operations of the target function through the calling behavior of the target leader wolf and the introduction of the loss function to complete the secondary processing.

5. The method for determining the cable force of a bridge according to claim 4, characterized in that: The step of initializing the wolf pack optimization algorithm to select q initial alpha wolves from the randomly generated N artificial wolves includes: Initializing the wolf pack optimization algorithm to determine the second target parameters of the wolf pack optimization algorithm; wherein the parameters include the size of the wolf pack, the dimension of the search space, the number of iterations, the step size factor, the wolf exploration scale factor, and the group update scale factor; According to the second target parameter, randomly generating N artificial wolves in the solution space; The objective function value of each artificial wolf is obtained in turn, and q artificial wolves that only meet preset conditions are screened out from the N objective function values ​​to serve as the initial leader wolf.

6. The method for determining the cable force of a bridge according to any one of claims 1 to 5, characterized in that: The step of collecting data of the same stay cable for multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber after the shock absorber is installed to form a second data set comprises: For the same inclined cable, a shock absorber is installed on the inclined cable; After installing the shock absorber, using a rubber hammer to perform multiple manual hammer excitations at any position on the cable; And after a preset time interval, data of the stay cable is collected multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber to form a second data group.

7. A device for determining the force of a bridge cable, characterized in that: include: A first data acquisition module, used for performing multiple data acquisitions before the shock absorber is installed to form a first data group; wherein the first data group includes an initial cable frequency, an initial cable force and an initial order; A second data collection module is used for collecting data of the same stay cable for multiple times at a position at a preset distance from a connection position between the stay cable and the shock absorber after the shock absorber is installed, so as to form a second data group; The result output module is used to input the first data group and the second data group into a target neural network model for prediction to obtain the cable force result of the inclined cable.

8. A device for determining the force of a bridge cable, characterized in that: The bridge cable force determination device comprises a processor and a memory, wherein a bridge cable force determination program is stored in the memory, and when the bridge cable force determination program is executed by the processor, the bridge cable force determination method according to any one of claims 1 to 6 is implemented.

9. A bridge cable force determination system, characterized in that: A shock absorber is provided on the inclined cable, and a connection position between the shock absorber and the inclined cable forms a detection position; The bridge stayed cable force determination system comprises: The bridge cable force determination device according to claim 8; A collection sensor, wherein the collection sensor is installed on the inclined cable, and the collection sensor is spaced apart from the detection position; and A data acquisition device is communicatively connected with the acquisition sensor and transmits the acquired data information to the bridge cable force determination device.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by one or more processors, the method for determining the cable force of a bridge cable according to any one of claims 1 to 6 is implemented.

Images